Search

We proposed and implemented a system based on fuzzy logic Toolbox. We designed such a system to measure the strength of the upper limb elbow of a tennis player. We have tried to predict the injuries and movements for the sports player, For that we used the Triangle and Trapezoidal membership function for better prediction of the elbow strength. We have selected Two input parameters Elbow Flexion Angle and Torque in the system development using fuzzy logic toolbox in Matlab. We have considered these two inputs and based on that we have developed membership functions. After we get the elbow strength levels we will be able to predict the level of injuries. By measuring the elbow strength, comments can be made on the chances of player getting elbow related injuries.

This paper addresses an approach for the classification of hyperspectral imagery (HSI). In remote sensing, the HSI sensor acquires hundreds of images with narrow and continuous spectral width in visible and near-infrared regions of the electromagnetic (EM) spectrum. Such nature of data acquisition is very useful in the classification and/or the identification of different objects present in the HSI data. However, the low-spatial resolution and large volume of HS images make it more challenging. In the proposed approach, we use an autoencoder with convolutional neural network (AECNN) for the classification of HS images. Pre-processing with autoencoder enhances the features in the HS images which helps to obtain optimized weights in the initial layers of the CNN model. Hence, shallow CNN architecture can be utilized to extract features from the pre-processed HSI data which are used further for the classification of the same. The potential of the proposed approach has been verified by conducting many experiments on various datasets. The classification results obtained using the proposed method are compared with many state-of-the-art deep learning based methods including the winner of the geoscience and remote sensing society (GRSS) Image Fusion Contest-2018 on HSI classification held at IEEE International Geoscience and Remote Sensing Symposium (IGARSS)-2018 and it shows superiority over those methods.

Trichilemmal carcinoma is rare cutaneous tumor affecting scalp, eyelids, neck and face. Generally seen in elderly women, it is large, often cystic and characterized by trichilemmal keratinization. However, it can have an aggressive clinical course propensity for distal metastasis. I report a case of 40 years old female who presented with scalp swelling in July 2019.She underwent wide local excision and histology revealed trichilemmal carcinoma. Patient lost to follow up and presented in 2022 with CT thorax showed lung metastasis and CT brain shows brain metastasis and she advised for palliative radiotherapy. Trichilemmal carcinoma with brain and lung metastasis is rare condition. The patient underwent palliative radiotherapy and expired 2 months after palliation.

Canopies represent sub-grid scale features in earth system models and interact as such with the large-scale processes resolved numerically. The canopy is implemented with a viscosity approach, resembling a roughness parameterization. However, the idea is that high viscosity is applied locally to an obstacle area whereas free spaces are assigned low viscosity. In a first step, we test this approach on a micro-scale, using an advection-diffusion equation to solve for tracer transport around obstacles. Available wind tunnel data are used for validation of a standard finite element implementation. In a second step, this approach is combined with a multi-scale finite element approach, such that a large-scale simulation can be coupled to the micro-scale representation of a canopy. Comparison of high-resolution standard finite element and low-resolution multi-scale finite element methods will allow for quantitative error analysis. This approach has the potential to lead to better parameterizations of subgrid-scale processes in large-scale simulations.

The first continuous flow process was developed to synthesize N-methyl secondary amines from alkyl mesylates and epoxides via a nucleophilic substitution using aqueous methylamine. A variety of N-m...

We present the case of imported malaria in pregnancy to the United Kingdom (UK) from Nigeria, where a 28-year-old primigravida presented to our maternity assessment unit (MAU) with complaints of pyrexia, rigors and passing dark coloured urine. She gave a travel history of recent migration from Nigeria 10 days before presenting to our emergency department. She initially became unwell five days after her arrival with general malaise and myalgia. On day six, she developed lower abdominal pain and observed that her urine was dark in colour. This prompted her to contact her general practitioner (GP). Treatment for a urinary tract infection was initiated by the GP after a phone consultation in keeping with COVID-19 contingency guidance, and the patient was prescribed antibiotics for three days. She presented to the emergency department two days after completing the course of antibiotics where she complained of worsening pelvic pain, reduced foetal movements and passing black urine. She was treated as suspected COVID-19 and red flag sepsis. Obstetric review led to investigation and diagnosis of severe malaria in pregnancy, which was accompanied by blackwater fever (BWF). The patient recovered after three doses of artesunate. An ultrasound scan of the foetus revealed a congenital cardiac anomaly, which had not been detected in an earlier scan. There was no evidence of congenital malaria in the neonate after delivery. There are several novel aspects in this case as maternal mortality in severe Plasmodium falciparum can be significantly high. Those who survive the disease in pregnancy are also known to develop several complications such as intrauterine death and preterm labour. There was also the component of blackwater fever, which is a rare event associated with severe malaria, and it also has a mortality rate. Significant in her medical history was a diagnosis of the sickle cell trait, and we postulate that this feature gave an added protection from the complications of severe malaria in pregnancy as well as blackwater fever.

The deep learning models for the Single Image Super-Resolution (SISR) task have found success in recent years. However, one of the prime limitations of existing deep learning-based SISR approaches is that they need supervised training. Specifically, the Low-Resolution (LR) images are obtained through known degradation (for instance, bicubic downsampling) from the High-Resolution (HR) images to provide supervised data as an LR-HR pair. Such training results in a domain shift of learnt models when real-world data is provided with multiple degradation factors not present in the training set. To address this challenge, we propose an unsupervised approach for the SISR task using Generative Adversarial Network (GAN), which we refer to hereafter as DUS-GAN . The novel design of the proposed method accomplishes the SR task without degradation estimation of real-world LR data. In addition, a new human perception-based quality assessment loss, i.e., Mean Opinion Score (MOS), has also been introduced to boost the perceptual quality of SR results. The pertinence of the proposed method is validated with numerous experiments on different reference-based (i.e., NTIRE Real-world SR Challenge validation dataset) and no-reference based (i.e., NTIRE Real-world SR Challenge Track-1 and Track-2) testing datasets. The experimental analysis demonstrates committed improvement from the proposed method over the other state-of-the-art unsupervised SR approaches, both in terms of subjective and quantitative evaluations on different reference metrics (i.e., LPIPS, PI-RMSE graph) and no-reference quality measures such as NIQE, BRISQUE and PIQE. We also provide the implementation of the proposed approach ( https://github.com/kalpeshjp89/DUSGAN ) to support reproducible research.

The prime limitation of optical sensors is the need for external sources of illumination while capturing the scene. This prevents them from recognizing objects in extreme conditions, such as insufficient illumination or severe weather (e.g., under fog or smoke). The thermal imaging sensors have been introduced to circumvent this deficiency, which acquires the image based on thermal radiation emitted by the objects. The technological advancement in thermal imaging enables the visualization of objects beyond the visible range that promotes its use in many principal applications, such as military, medical, agriculture, etc. However, hardware point of view, the cost of a thermal camera is prohibitively higher than that of an equivalent optical sensor. This led to employ software-driven approaches called super-resolution (SR) to enhance the resolution of given thermal images. We propose a deep neural network architecture referred to as “ThermISRnet” as the extension of our earlier winner architecture in the Perception Beyond the Visible Spectrum (PBVS) thermal SR challenge. We use a progressive upscaling strategy with asymmetrical residual learning in the network, which is computationally efficient for different upscaling factors such as ×2, ×3, and ×4. The proposed architecture consists of different modules for low- and high-frequency feature extraction along with upsampling blocks. The effectiveness of the proposed architecture in ThermISRnet is verified by evaluating it with different datasets. The obtained results indicate superior performance as compared to other state-of-the-art SR methods.

This paper presents results from the second Thermal Image Super-Resolution (TISR) challenge organized in the framework of the Perception Beyond the Visible Spectrum (PBVS) 2021 workshop. For this second edition, the same thermal image dataset considered during the first challenge has been used; only mid-resolution (MR) and high-resolution (HR) sets have been considered. The dataset consists of 951 training images and 50 testing images for each resolution. A set of 20 images for each resolution is kept aside for evaluation. The two evaluation methodologies proposed for the first challenge are also considered in this opportunity. The first evaluation task consists of measuring the PSNR and SSIM between the obtained SR image and the corresponding ground truth (i.e., the HR thermal image downsampled by four). The second evaluation also consists of measuring the PSNR and SSIM, but in this case, considers the ×2 SR obtained from the given MR thermal image; this evaluation is performed between the SR image with respect to the semi-registered HR image, which has been acquired with another camera. The results out-performed those from the first challenge, thus showing an improvement in both evaluation metrics.

This work reviews the results of the NTIRE 2021 Challenge on Non-Homogeneous Dehazing. The proposed techniques and their results have been evaluated on a novel dataset that extends the NH-Haze datset. It consists of additional 35 pairs of real haze free and nonhomogeneous hazy images recorded outdoor. The nonhomogeneous haze has been introduced in the outdoor scenes by using a a professional setup that imitates the real conditions of haze scenes. 327 participants registered in the challenge and 23 teams competed in the final testing phase. The proposed solutions gauge the state-of-the-art in image dehazing.

The ability of thermal sensors to penetrate smoke, mist, dust and aerosol makes them attractive for deployment in essential applications in military, medical, agricultural and animal ecology over the regular optical cameras. However, unlike optical imaging devices, the most sophisticated commercial thermal imaging sensor does not match the megapixel imaging ability. The Low-Resolution (LR) images from thermal sensors can be enhanced through a software-driven solution called Super-Resolution (SR). A number of works have been proposed to employ deep networks for SR task; however, they are overloaded with redundant features due to the deep architecture. This paper introduces a Channel Splitting-based Convolutional Neural Network (ChasNet) for thermal image SR eliminating the redundant features in the network. The use of channel splitting extracts the versatile features from Low-Resolution (LR) thermal image, helping to preserve high-frequency details in the SR images. We demonstrate the applicability proposed network for SR task in two different scenarios organized in the PBVS-2021 Thermal SR Challenge, consisting of noise elimination (Track-1) and domain shifting (Track-2). The efficacy is justified by comparing the SR results with other state-of-the-art thermal SR techniques in qualitative and quantitative metrics. A set of extensive experiments separately analyzes the importance of each block in the proposed architecture. The code of this work is also published online1.

This paper reviews the NTIRE 2021 challenge on learning the super-Resolution space. It focuses on the participating methods and final results. The challenge addresses the problem of learning a model capable of predicting the space of plausible super-resolution (SR) images, from a single low-resolution image. The model must thus be capable of sampling diverse outputs, rather than just generating a single SR image. The goal of the challenge is to spur research into developing learning formulations and models better suited for the highly ill-posed SR problem. And thereby advance the state-of-the-art in the broader SR field. In order to evaluate the quality of the predicted SR space, we propose a new evaluation metric and perform a comprehensive analysis of the participating methods. The challenge contains two tracks: 4× and 8 scale factor. In total, 11 teams competed in the final testing× phase.

As the quality of mobile cameras starts to play a crucial role in modern smartphones, more and more attention is now being paid to ISP algorithms used to improve various perceptual aspects of mobile photos. In this Mobile AI challenge, the target was to develop an end-to-end deep learning-based image signal processing (ISP) pipeline that can replace classical hand-crafted ISPs and achieve nearly real-time performance on smartphone NPUs. For this, the participants were provided with a novel learned ISP dataset consisting of RAW-RGB image pairs captured with the Sony IMX586 Quad Bayer mobile sensor and a professional 102-megapixel medium format camera. The runtime of all models was evaluated on the MediaTek Dimensity 1000+ platform with a dedicated AI processing unit capable of accelerating both floating-point and quantized neural networks. The proposed solutions are fully compatible with the above NPU and are capable of processing Full HD photos under 60-100 milliseconds while achieving high fidelity results. A detailed description of all models developed in this challenge is provided in this paper., Mobile AI 2021 Workshop and Challenges: https://ai-benchmark.com/workshops/mai/2021/

Introduction: This study investigated the effect of coronavirus disease 2019 (COVID-19) lockdown on the incidence of ocular trauma in children. Methods: In this retrospective cohort study, we collected data of pediatric patients who presented with ocular trauma in the emergency department during the lockdown period (from 22 March, 2020, to 30 May, 2020). In addition, we collected data of patients presenting with ocular trauma during the same period in the previous year. We compared the number of patients who underwent ocular surgery and the number of paediatric patients with ocular trauma between these two periods. A confounding factor may be the absence of patients from different districts who could not travel to the centre due to travel restrictions. Results: Between 22 March, 2019, and May 2019, a total of 156 (17%) of total opd patients presented with ocular trauma, of whom 28(27.8%) required surgery. By contrast, between 22 March, 2020, and May 2020, a total of 92(33.9%) of total outdoor patients presented with ocular trauma, of whom 25(65.7) % required surgery. Conclusions: Covid-19 lockdown exerted a significant effect on the incidence of ocular trauma in pediatric population.

Chronic pancreatitis (CP), secondary to a wide variety of etiologies, is a progressive and irreversible disease. Initially, CP is managed with endoscopic interventions, long-term analgesia for its associated chronic abdominal pain syndrome and pancreatic enzyme replacement for exocrine dysfunction. As the disease advances, pancreatic drainage procedures and partial resections are considered, but they leave diseased tissue behind and usually result in short-term relief only. Total pancreatectomy alone is widely viewed as a last resort treatment option because it causes brittle diabetes mellitus. However, total pancreatectomy with islet autotransplantation (TPIAT) can prevent the development of diabetes and cure the chronic pain syndrome. One serious, albeit rare, complication of TPIAT is (partial) portal vein thrombosis. Its incidence is probably about 5%. To prevent the occurrence of portal vein thrombosis, we propose herein, and have successfully performed, continuous real-time Doppler ultrasonography during the islet infusion to study portal vein and intrahepatic flow patterns, as well as changes in Doppler signals. Flow and signal changes may allow for timely adjustment of the infusion rate, before a marked increase in portal vein pressure is noted and decrease the risk of portal vein thrombosis.

Urban canopies consist of buildings and trees that are aligned along a street in the horizontal direction. These canopies in cities and forests modulate the local climate considerably in a complex way. Canopies constitute very fine subgrid features that actually have a significant impact on other components of earth system models but their feedbacks on larger scales are by now represented in rather heuristic ways. The problem in simulating their impact is twofold: First, their local modeling is delicate and, secondly, the numerical modeling of the scale interaction between fine and large scales is complicated since the fine scale structure is global. We will mostly focus on the second aspect. Multiscale finite element methods (MsFEM) in their classical form have been applied to various porous media problems but the situation in climate, and hence flow-dominated regimes is different from porous media applications. In order to study the effect of various parameters like the concentration of pollutants, or the dynamics of the background velocity and of the temperature in the atmospheric boundary layer, a semi-Lagrangian reconstruction based multiscale finite element framework (SLMsR) developed by [1, 2] for passive tracer transport modeled by an advection-diffusion equation with high-contrast oscillatory diffusion is applied. These methods are composed of two parts: a local-in-time semi-Lagrangian offline phase that pre-computes basis functions and an online phase that uses these basis functions to compute the solution on a coarse Eulerian simulation mesh. The overhead of pre-computing the basis functions in each coarse block can further be reduced by parallelization. The online phase is approximately as fast as a low resolution standard FEM but using the modified basis that carries subgrid information still allows to reveal the fine scale features of a highly resolved solution and is therefore accurate. This approach is studied in order to reveal the feedback of processes in the canopy layer on different scales present in climate simulation models and in particular on the atmospheric boundary layer. We will show the results of massively parallel simulations for passive tracer transport in an urban region using the new multiscale approach and compare them to classical approaches.References :[1] Simon, Konrad, and Jörn Behrens. "Semi-Lagrangian Subgrid Reconstruction for Advection-Dominant Multiscale Problems.", Springer Journal of Scientific Computing (JOMP) (provisionally accepted), 2019[2] Simon, Konrad, and Jörn Behrens. "Multiscale Finite Elements for Transient Advection-Diffusion Equations through Advection-Induced Coordinates.", Multiscale Modeling & Simulation 18.2 (2020): 543-571.

We address an approach called “DepthFuseNet” for the fusion of thermal and visible images using convolutional neural networks (CNN). The thermal image acquires radiating energy of the sensed objects and hence it can easily distinguish the objects from its background. However, the visible image (i.e., the image acquired within the range of visible wavelength of electromagnetic spectrum) provides a more visual context of the objects with high spatial resolution. Due to this complement nature of thermal and visible images, it is always an interest of the community to combine those two images to obtain more meaningful information from the individual source images. In DepthFuseNet method, features are extracted from given source images using CNN architecture, and they are integrated using the different fusion strategies. The auto-weighted sum fusion strategy performs better than that obtained using the other existing methods. To reduce the complexity of the architecture, we use depthwise convolution in the network. The experimental evaluation demonstrates that the proposed method exhibits salient features from the source images, and hence it performs better than the other state-of-the-art fusion methods in terms of qualitative and quantitative assessments.

Convolutional Neural Networks (CNNs) have shown promising results on Single Image Super-Resolution (SISR) task. A pair of Low-Resolution (LR) and High-Resolution (HR) images are typically used in the CNN models to train them to super-resolve LR images in a fully supervised manner. Owing to non-availability of true LR-HR pairs, the LR images are generally synthesized from HR data by applying synthetic degradation such as bicubic downsampling. Such networks under-perform when used on real-world data where degradation is different from the synthetically generated LR image. As obtaining true LR-HR pair is a tedious and resource (time and effort) consuming task, we propose a new approach and architecture to super-resolve the real-world LR images in an unsupervised manner by using a Generative Adversarial Network (GAN) framework with Variational Auto-Encoder (VAE). Along with a new network architecture, we also introduce a novel loss metric based on no-reference quality scores of SR images to improve the perceptual fidelity of the SR images. Through the experiments on NTIRE-2020 Real-World SR Challenge dataset, we demonstrate the superiority of the proposed approach over the other competing state-of-the-art methods.

The current state-of-the-art deep learning based Single Image Super-Resolution (SISR) techniques employ supervised learning in the training process. In this learning, the Low-Resolution (LR) images are prepared by applying known degradation such as bicubic downsampling to the High-Resolution (HR) images. Unfortunately, bicubic down-sampling eliminates the natural image characteristics such as sensor noise, degradation due to built-in hardware, etc., and generates smooth images and hence generated images are different from the real-world data. When deep learning model is trained using such artificially generated LR-HR pairs, they often are prone to generate better SR results for real-world images. To circumvent this problem, we propose an SR framework that can train in an unsupervised manner using Generative Adversarial Networks (GANs). It contains mainly couple of networks called SR network and degradation network which work on an unpaired data of LR-HR images. The SR network learns to eliminate noise present in the LR image and super-resolve it. While, degradation network performs inverse of SR network (i.e. down-sampling and adding degradation from real-world images). We demonstrate the effectiveness of the proposed method by conducting extensive experiments on NTIRE-2020 Real-world SR challenge dataset where it demonstrates the superior performance over state-of-the-art methods in terms of both quantitative and qualitative assessments.

Introduction: This study investigated the effect of coronavirus disease 2019 (COVID-19) lockdown on the incidence of ocular trauma.Methods: In this retrospective cohort study, we collected data of patients who presented with ocular trauma in the emergency department during the lockdown period (from 22 March, 2020, to 30 April, 2020). In addition, we collected data of patients presenting with ocular trauma during the same period in the previous year. We compared the number of patients who underwent ocular surgery and the number of paediatric patients with ocular trauma between these two periods. A confounding factor may be the absence of patients from different districts who could not travel to the centre due to travel restrictions.Results: Between 22 March, 2019, and 30 April, 2019, a total of 76 patients presented with ocular trauma, of whom 28( 37.2%) required surgery. By contrast, between 22 March, 2020, and 30 April, 2020, a total of 78 patients presented with ocular trauma, of whom 33(42)% required surgery. Furthermore, 9% and 30% of the total patients in 2019 and 2020, respectively, belonged to the paediatric age group. Conclusions: COVID-19 lockdown exerted a significant effect on the incidence of ocular trauma.

Background Treatment with vesatolimod, an investigational, oral, toll-like receptor 7 (TLR7) agonist, leads to sustained viral remission in some non-human primates when combined with anti-envelope antibodies or therapeutic vaccines. We report results of a Phase Ib study evaluating safety, pharmacokinetics, and pharmacodynamics of vesatolimod in adults living with human immunodeficiency virus (HIV)–1. Methods In this double-blind, multicenter, placebo-controlled trial, participants on antiretroviral therapy with screening plasma HIV-1 RNA levels Results A total of 48 individuals were randomly assigned to vesatolimod (n = 36) or placebo (n = 12). Vesatolimod was generally well tolerated, with no study drug–related serious adverse events or adverse events leading to study drug discontinuation. There were no statistically significant changes from baseline in plasma HIV-1 RNA in the vesatolimod groups, compared to placebo. Vesatolimod plasma exposures increased dose proportionally; consistent responses in cytokines, interferon-stimulated gene expression, and lymphocyte activation were observed with increasing dose levels above 4 mg. Peak elevations 24 hours after receipt of a 6 mg dose were >3.9-fold higher for interferon gamma-induced protein 10 (IP-10), interleukin-1 receptor antagonist (IL-1RA), interferon–inducible T-cell alpha chemoattractant (ITAC) when compared to baseline values. Conclusions Vesatolimod was well tolerated at doses ranging from 1 to 12 mg. Immune stimulation was observed at doses above 4 mg, providing rationale for future combination trials in people living with HIV. Clinical Trials Registration NCT02858401.

This paper represents an approach while designing the 3D printed hand for the amputees for fulfilling their daily routine task. It is quite a complex mechanism to deal with brain signals. This paper presents the most affordable technique to measure the signals through low-cost EEG headset. The data from the headset is processed and transmitted to the hardware of the system which uses a certain control mechanism for movement of fingers and hand. This type of device is used in such patients having neurological disorders such as brain stroke or has lost their limbs in case of fatal accidents. The aim of designing such a Neuroprosthetic hand is to provide natural movement through brain signals and also eliminate the need for any surgery. A Neuroprosthetic hand can be customized for an amputee with their needs and requirements. More natural movement is also a basic requirement on which this proposed model is emphasized So, an efficient alternative approach is implemented here to design such noninvasive, efficient, affordable solutions for an amputee.

This paper summarizes the top contributions to the first challenge on thermal image super-resolution (TISR), which was organized as part of the Perception Beyond the Visible Spectrum (PBVS) 2020 workshop. In this challenge, a novel thermal image dataset is considered together with state- of-the-art approaches evaluated under a common framework. The dataset used in the challenge consists of 1021 thermal images, obtained from three distinct thermal cameras at different resolutions (low-resolution, mid-resolution, and high-resolution), resulting in a total of 3063 thermal images. From each resolution, 951 images are used for training and 50 for testing while the 20 remaining images are used for two proposed evaluations. The first evaluation consists of downsampling the low-resolution, mid-resolution, and high-resolution thermal images by ×2, ×3 and ×4 respectively, and comparing their super-resolution results with the corresponding ground truth images. The second evaluation is comprised of obtaining the ×2 super-resolution from a given mid-resolution thermal image and comparing it with the corresponding semi-registered high- resolution thermal image. Out of 51 registered participants, 6 teams reached the final validation phase., info:eu-repo/semantics/published

Surveillance has become an important task in recent time mainly due to the increasing of crime rates. The existing research on surveillance for day time has achieved better performance by detecting and tracking objects using deep learning algorithms. However, it is difficult to achieve the same performance for night vision mainly due to low illumination and/or bad weather situation. One of the important tasks in surveillance is object detection which results in both class and location of the detected object with clear boundary of the objects from the image. We propose an efficient object detection module using fusion of thermal and visible images. Fusion module consists of encoder-decoder network in which encoder uses depthwise convolution to extracts efficient features from the given thermal and visible images. Then after, fused image is reconstructed using convolutional layers and final map is utilized in object detection algorithm (i.e., mask RCNN). The proposed method shows the effectiveness of utilization of pre-processing module i.e., fusion in object detection algorithm. Here, it is observed that the proposed method performs better for night vision when images are trained carefully with various features. Moreover, proposed method performs better on real time night vision images having no illumination condition.

Human perception is limited to perceive the objects beyond the range of visible wavelengths in the Electromagnetic (EM) spectrum. This prevents them to recognize objects in different conditions such as poor illumination or severe weather (e.g., under fog or smoke). The technological advancement in thermographic imaging enables the visualization of objects beyond visible range which enables it's use in many applications such as military, medical, agriculture, etc. However, due to the hardware constraints, the thermal cameras are limited with poor spatial resolution when compared to similar visible range RGB cameras. In this paper, we propose a Super-Resolution (SR) of thermal images using a deep neural network architecture which we refer to as TherISuRNet. We use progressive upscaling strategy with asymmetrical residual learning in the network which is computationally efficient for different upscaling factors such as ×2, ×3 and ×4. The proposed architecture consists of different modules for low and high-frequency feature extraction along with upsampling blocks. The effectiveness of the proposed architecture in TherISuRNet is verified by evaluating it with different datasets. The obtained results indicate superior results as compared to other state-of-the-art SR methods.

We present a novel architecture to fuse thermal and visible images using deep learning algorithms. As infrared images contain higher information, an object can be distinguished from its background due to radiation difference and work well in all conditions such as bad weather and night time. Contrast to that, visible images provide texture information with high spatial resolution or visual context of the objects. Therefore, it is advisable to fuse infrared and visible images which can combine the advantages of thermal radiation information and detailed texture information. Compared to traditional methods of convolutional networks, our proposed network extracts more salient features from individual images by introducing depthwise convolution in the network which reduces more number of parameters. Then after, features from two different sources are fused and an image is reconstructed by decoder network. We compare our proposed method with other state-of-the-art methods, which outperforms on qualitative and quantitative assessment.

Nowadays, prosthetic field has seen many accomplishments and success by the use of different technological advanced techniques. Prosthetic hands are made out of very high-quality materials but at the same time they are very expensive. There are different techniques available for designing prosthetic hand but most of these techniques have some problems; they are extremely expensive, very hard to install and may require operative surgery before using them. Most of the amputees who require upper limb amputation do not prefer to go for highly expensive prosthesis despite of their high quality. Therefore, the idea is to introduce the initial design of an EEG based controlled smart prosthetic hand which can be treated as customised solution. In our approach we controlling prosthetic hands by the brain waves, obtained from an electroencephalography (EEG) headset. The EEG-based headset (Mind wave Mobile) designed by Neurosky is used to communicate with human brains. The device tries to resemble like natural hand movement as the brain part is involved in it. The movement of biological neuroprosthetic hand by signal acquisition through neurosky headset. The brain waves are sensed by sensors in the neurosky headset and then this signal is processed by the processing system which detects the different levels of attention and meditation through headset. When the system detects that the attention meter value indicates the high attention level it gives command signal to the servo motors so it drives forward, and hand starts closing. If an amputee wants to open the hand to release an object, he/she needs to be in relaxing position and that in turn reduces level of the attention meter value. It senses by control system and that gives command to servo motor which move backward and close hand. According to the level, hand movement can be generated. It is used for an amputee below the elbow.

This paper addresses an approach for classification of hyperspectral imagery (HSI). In remote sensing, the HSI sensor acquires hundreds of images with very narrow but continuous spectral width in visible and near-infrared regions of the electromagnetic (EM) spectrum. Due to the nature of data acquisition with contiguous bands, the HS images are very useful in classification and/or the identification of materials present in the captured geographical area. However, the low spatial resolution and large volume of HS images make the classification of those images as a challenging task. In the proposed approach, we use an autoencoder with convolutional neural network (AECNN) for classification of HS image. Pre-processing procedure with autoencoder leads to obtain optimized weights in the initial layer of CNN model. Moreover, features are enhanced in the HS images by utilizing the autoencoder. The CNN is used for efficient extraction of the features and same is also utilised for the classification of HS data. The potential of the proposed approach has been verified by conducting the experiments on three recent datasets. The experimental results are compared with the results obtained in the geoscience and remote sensing society (GRSS) Image Fusion Contest-2018 held at IEEE International Geoscience and Remote Sensing Symposium (IGARSS)-2018 and other existing frameworks for HSI classification. The testing accuracy of classification for the proposed approach is better than that of the other existing deep learning based methods.